A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 14:45 UTC
[CPU][Bugfix] Fix CPU docker issues (#16454)
Signed-off-by: jiang.li <jiang1.li@intel.com>
Li, Jiang committed
Apr 11, 2025 at 14:19 UTC
dda811021a5d58746583db1f3060929f3e6d90e0
1 file changed
+3
docker/Dockerfile.cpu
+3
@@ -18,6 +18,8 @@ WORKDIR /workspace/
18
ARG PYTHON_VERSION=3.12
19
ARG PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu"
20
21
+ENV LD_PRELOAD=""
22
+
23
# Install minimal dependencies and uv
24
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
25
--mount=type=cache,target=/var/lib/apt,sharing=locked \
@@ -32,6 +34,7 @@ ENV CMAKE_CXX_COMPILER_LAUNCHER=ccache
34
35
ENV PATH="/root/.local/bin:$PATH"
36
ENV VIRTUAL_ENV="/opt/venv"
37
+ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
38
RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
39
ENV PATH="$VIRTUAL_ENV/bin:$PATH"
40